Abstract
In this paper, we propose an effective method of \(\hbox {PM}_{2.5}\) prediction based on image contrast-sensitive features and weighted bagging based neural network (WBBNN). Three types of image contrast-sensitive features are first extracted from the images and fuzzified. Next, a weighted bagging strategy combining the ensemble fuzzy neural network (FNN) and ensemble radial basis function neural network (RBFNN) is established. The ensemble neural network (NN), regardless of FNN and RBFNN, is obtained by simply averaging the outputs of component neural networks. And these component neural networks are trained by the improved gradient descent algorithm and samples acquired by bootstrap sampling. Finally, the WBBNN is used to forecast \(\hbox {PM}_{2.5}\) concentration by extracting three types of image contrast-sensitive features. Results of experiments demonstrate that our prediction method is more reliable, practical and efficient than FNN, RBFNN, the ensemble NNs, and state-of-the-art quality assessment method in terms of predicting the concentration of \(\hbox {PM}_{2.5}\). More importantly, an improved gradient descent algorithm is developed to accelerate the convergence speed and ensure the prediction accuracy of WBBNN and the fuzzy features acquired by the feature fuzzification method can greatly improve the robustness and precision of WBBNN.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Anderson TL, Ogren JA (1998) Determining aerosol radiative properties using the TSI 3563 integrating nephelometer. Aerosol Sci Technol 29(1):57–69. https://doi.org/10.1080/02786829808965551
Azid A, Juahir H, Toriman ME, Kamarudin MKA, Saudi ASM, Hasnam CNC, Aziz NAA, Azaman F, Latif MT, Zainuddin SFM et al (2014) Prediction of the level of air pollution using principal component analysis and artificial neural network techniques: a case study in Malaysia. Water Air Soil Pollut 225(8):2063. https://doi.org/10.1007/s11270-014-2063-1
Bologna G, Yvon C, Duvaud S, Veuthey AL (2004) N-terminal myristoylation predictions by ensembles of neural networks. Proteomics 4(6):1626–1632. https://doi.org/10.1002/pmic.200300783
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140. https://doi.org/10.1007/BF00058655
Broomhead DS, Lowe D (1988) Radial basis functions, multi-variable functional interpolation and adaptive networks. Tech. Rep. RSRE-MEMO-4148
Choi LK, You J, Bovik AC (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–3901. https://doi.org/10.1109/TIP.2015.2456502
Davis BL, Guo JX (2000) Airborne particulate study in five cities of China. Atmos Environ 34(17):2703–2711. https://doi.org/10.1016/S1352-2310(99)00528-2
Elangasinghe MA, Singhal N, Dirks KN, Salmond JA, Samarasinghe S (2014) Complex time series analysis of PM10 and PM2.5 for a coastal site using artificial neural network modelling and k-means clustering. Atmos Environ 94:106–116. https://doi.org/10.1016/j.atmosenv.2014.04.051
Elbayoumi M, Ramli NA, Yusof NFFM, Yahaya ASB, Madhoun WA, Ul-Saufie AZ (2014) Multivariate methods for indoor PM10 and PM2.5 modelling in naturally ventilated schools buildings. Atmos Environ 94:11–21. https://doi.org/10.1016/j.atmosenv.2014.05.007
Ferreira J, Guevara M, Baldasano JM, Tchepel O, Schaap M, Miranda AI, Borrego C (2013) A comparative analysis of two highly spatially resolved european atmospheric emission inventories. Atmos Environ 75:43–57. https://doi.org/10.1016/j.atmosenv.2013.03.052
Fu ML, Wang WW, Le ZC, Khorram MS (2015) Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model. Neural Comput Appl 26(8):1789–1797. https://doi.org/10.1007/s00521-015-1853-8
Groen II, Ghebreab S, Prins H, Lamme VA, Scholte HS (2013) From image statistics to scene gist: evoked neural activity reveals transition from low-level natural image structure to scene category. J Neurosci 33(48):18814–18824. https://doi.org/10.1523/JNEUROSCI.3128-13.2013
Gu K, Wang SQ, Zhai GT, Ma SW, Yang XK, Lin WS, Zhang WJ, Gao W (2016a) Blind quality assessment of tone-mapped images via analysis of information, naturalness, and structure. IEEE Trans Multimed 18(3):432–443. https://doi.org/10.1109/TMM.2016.2518868
Gu K, Zhai GT, Lin WS, Liu M (2016b) The analysis of image contrast: from quality assessment to automatic enhancement. IEEE Trans Cybern 46(1):284–297
Gu K, Lin WS, Zhai GT, Yang XK, Zhang WJ, Chen CW (2017) No-reference quality metric of contrast-distorted images based on information maximization. IEEE Trans Cybern 47(12):4559–4565. https://doi.org/10.1109/TCYB.2016.2575544
Gu K, Qiao JF, Li XL (2018a) Highly efficient picture-based prediction of PM2.5 concentration. IEEE Trans Ind Electron 66(4):3176–3184. https://doi.org/10.1109/TIE.2018.2840515
Gu K, Qiao JF, Lin WS (2018b) Recurrent air quality predictor based on meteorology-and pollution-related factors. IEEE Trans Ind Inform 14(9):3946–3955. https://doi.org/10.1109/TII.2018.2793950
Gu K, Tao DC, Qiao JF, Lin WS (2018c) Learning a no-reference quality assessment model of enhanced images with big data. IEEE Trans Neural Netw Learn Syst 29(4):1301–1313. https://doi.org/10.1109/TNNLS.2017.2649101
Han HG, Li Y, Qiao JF (2014) A fuzzy neural network approach for online fault detection in waste water treatment process. Comput Electr Eng 40(7):2216–2226. https://doi.org/10.1016/j.compeleceng.2014.08.011
Han HG, Lin ZL, Qiao JF (2017) Modeling of nonlinear systems using the self-organizing fuzzy neural network with adaptive gradient algorithm. Neurocomputing 266:566–578. https://doi.org/10.1016/j.neucom.2017.05.065
Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12(10):993–1001. https://doi.org/10.1109/34.58871
Hasler D, Suesstrunk SE (2003) Measuring colorfulness in natural images. Proc SPIE 5007:87–96. https://doi.org/10.1117/12.477378
Hauck H, Berner A, Gomiscek B, Stopper S, Puxbaum H, Kundi M, Preining O (2004) On the equivalence of gravimetric PM data with teom and beta-attenuation measurements. J Aerosol Sci 35(9):1135–1149. https://doi.org/10.1016/j.jaerosci.2004.04.004
Hsu KW (2013) Weight-adjusted bagging of classification algorithms sensitive to missing values. IJIT 3(5):560. https://doi.org/10.7763/IJIET.2013.V3.335
Huang W, Tan JG, Kan HD, Zhao N, Song WM, Song GX, Chen GH, Jiang LL, Jiang C, Chen RJ et al (2009) Visibility, air quality and daily mortality in Shanghai, China. Sci Total Environ 407(10):3295–3300. https://doi.org/10.1016/j.scitotenv.2009.02.019
Jing L, Chen B, Zhang BY (2014) Modeling of UV-induced photodegradation of naphthalene in marine oily wastewater by artificial neural networks. Water Air Soil Pollut 225(4):1906. https://doi.org/10.1007/s11270-014-1906-0
Johnson RW (2001) An introduction to the bootstrap. Teach Stat 23(2):49–54. https://doi.org/10.1111/1467-9639.00050
Li XB, Wang DF, Lu QC, Peng ZR, Fu QY, Hu XM, Huo JT, Xiu GL, Li B, Li C et al (2018) Three-dimensional analysis of ozone and PM2.5 distributions obtained by observations of tethered balloon and unmanned aerial vehicle in Shanghai, China. Stoch Environ Res Risk Assess 32(5):1189–1203. https://doi.org/10.1007/s00477-018-1524-2
Liu CB, Tsow F, Zou Y, Tao NJ (2016) Particle pollution estimation based on image analysis. PLoS ONE 11(2):e0145955. https://doi.org/10.1371/journal.pone.0145955
Macias ES, Husar RB (1976) Atmospheric particulate mass measurement with beta attenuation mass monitor. Environ Sci Technol 10(9):904–907. https://doi.org/10.1021/es60120a015
Mishra D, Goyal P, Upadhyay A (2015) Artificial intelligence based approach to forecast PM2.5 during haze episodes: a case study of Delhi, India. Atmos Environ 102:239–248. https://doi.org/10.1016/j.atmosenv.2014.11.050
Muir D, Laxen DPH (1995) Black smoke as a surrogate for PM10 in health studies? Atmos Environ 29(8):959–962. https://doi.org/10.1016/1352-2310(94)00370-Z
Nie JH, Linkens DA (1993) Learning control using fuzzified self-organizing radial basis function network. IEEE Trans Fuzzy Syst 1(4):280–287. https://doi.org/10.1109/91.251928
Ordieres JB, Vergara EP, Capuz RS, Salazar RE (2005) Neural network prediction model for fine particulate matter (PM2.5) on the US–Mexico border in El Paso (Texas) and Ciudad Juárez (Chihuahua). Environ Model Softw 20(5):547–559. https://doi.org/10.1016/j.envsoft.2004.03.010
Qiao JF, Wang GM, Li XL, Li WJ (2018) A self-organizing deep belief network for nonlinear system modeling. Appl Soft Comput 65:170–183. https://doi.org/10.1016/j.asoc.2018.01.019
Riccio A, Chianese E, Agrillo G, Esposito C, Ferrara L, Tirimberio G (2014) Source apportion of atmospheric particulate matter: a joint Eulerian/Lagrangian approach. Environ Sci Pollut Res 21(23):13160–13168. https://doi.org/10.1007/s11356-013-2367-5
Ruppecht E, Meyer M, Patashnick H (1992) The tapered element oscillating microbalance as a tool for measuring ambient particulate concentrations in real time. J Aerosol Sci 23:635–638. https://doi.org/10.1016/0021-8502(92)90492-E
Scholte HS, Ghebreab S, Waldorp L, Smeulders AW, Lamme VA (2009) Brain responses strongly correlate with weibull image statistics when processing natural images. J Vision 9(4):29–29. https://doi.org/10.1167/9.4.29
Smith JD, Atkinson DB (2001) A portable pulsed cavity ring-down transmissometer for measurement of the optical extinction of the atmospheric aerosol. Analyst 126(8):1216–1220. https://doi.org/10.1039/B101491I
Vu PV, Chandler DM (2012) A fast wavelet-based algorithm for global and local image sharpness estimation. IEEE Signal Process Lett 19(7):423–426. https://doi.org/10.1109/LSP.2012.2199980
Wang GM, Jia QS, Qiao JF, Bi J, Liu CX (2020) A sparse deep belief network with efficient fuzzy learning framework. Neural Netw 121:430–440
Xiao S, Wang QY, Cao JJ, Huang RJ, Chen WD, Han YM, Xu HM, Liu SX, Zhou YQ, Wang P et al (2014) Long-term trends in visibility and impacts of aerosol composition on visibility impairment in Baoji, China. Atmos Res 149:88–95. https://doi.org/10.1016/j.atmosres.2014.06.006
Ye C, Chen RS, Chen MX, Ye XY (2019) A new framework of regional collaborative governance for PM2.5. Stoch Environ Res Risk Assess 33(4–6):1109–1116. https://doi.org/10.1007/s00477-019-01688-w
Yu L, Wang SY, Lai KK (2008a) Credit risk assessment with a multistage neural network ensemble learning approach. Expert Syst Appl 34(2):1434–1444. https://doi.org/10.1016/j.eswa.2007.01.009
Yu L, Wang SY, Lai KK (2008b) Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Econ 30(5):2623–2635. https://doi.org/10.1016/j.eneco.2008.05.003
Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353. https://doi.org/10.1016/S0019-9958(65)90241-X
Zhang GP, Berardi VL (2001) Time series forecasting with neural network ensembles: an application for exchange rate prediction. J Oper Res Soc 52(6):652–664. https://doi.org/10.1057/palgrave.jors.2601133
Zhang YL, Cao F (2015) Fine particulate matter (PM2.5) in China at a city level. Sci Rep 5:14884. https://doi.org/10.1038/srep14884
Zhou ZH, Wu J, Tang W (2002) Ensembling neural networks: many could be better than all. Artif Intell 137(1–2):239–263. https://doi.org/10.1016/S0004-3702(02)00190-X
Acknowledgements
This work is supported by the Key Project of National Natural Science Foundation of China (Nos. 61533002 and 61803006), the National Science and Technology Major Project (No. 2018ZX07111005), the National Science Foundation of China under Grants (No. 61890930-5), the National Key Research and Development Project under Grant (No. 2018YFC1900800-5).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qiao, J., He, Z. & Du, S. Prediction of \(\hbox {PM}_{2.5}\) concentration based on weighted bagging and image contrast-sensitive features. Stoch Environ Res Risk Assess 34, 561–573 (2020). https://doi.org/10.1007/s00477-020-01787-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-020-01787-z